© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14136
    Prev
    Next
    INDEX
    Explanations

    say "definition"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    的职业
    -17.75
    clientId
    -16.13
    balance
    -16.13
    \Configuration
    -15.69
    冕
    -15.63
    esto
    -15.50
     communicator
    -15.44
    лож
    -15.44
    WXYZ
    -15.25
     configuration
    -15.19
    POSITIVE LOGITS
     senses
    16.25
    在线
    15.56
    Definitions
    15.50
    ˈ
    15.00
    definition
    15.00
     definitions
    14.88
     Definitions
    14.44
     definition
    14.38
     sense
    14.25
    定义
    14.25
    Activations Density 0.119%

    No Known Activations